© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234172
    Prev
    Next
    INDEX
    Explanations

    BERT

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     பசு
    0.39
    gb
    0.39
     hijacking
    0.38
     patches
    0.37
     figures
    0.37
     Asalamualaikum
    0.36
     decreasing
    0.36
     छ
    0.36
     charger
    0.36
    呫
    0.36
    POSITIVE LOGITS
     Developers
    0.47
     개발
    0.47
    Developers
    0.47
     ontwikk
    0.46
    DEV
    0.45
     डेवलप
    0.45
    睺
    0.44
     базе
    0.44
     DEV
    0.44
     Entwick
    0.43
    Activations Density 0.003%

    No Known Activations